sh: oprofile: Use perf-events oprofile backend
Now that we've got a generic perf-events based oprofile backend we might as well make use of it seeing as SH doesn't do anything special with its oprofile backend. Also introduce a new CONFIG_HW_PERF_EVENTS symbol so that we can fallback to using the timer interrupt for oprofile if the CPU doesn't support perf events. Also, to avoid a section mismatch warning we need to annotate oprofile_arch_exit() with an __exit marker. Signed-off-by: Matt Fleming <matt@console-pimps.org> Acked-by: Paul Mundt <lethal@linux-sh.org> Signed-off-by: Robert Richter <robert.richter@amd.com>
This commit is contained in:
parent
3d90a00763
commit
86c8c04792
4 changed files with 41 additions and 126 deletions
|
@ -249,6 +249,11 @@ config ARCH_SHMOBILE
|
||||||
select PM
|
select PM
|
||||||
select PM_RUNTIME
|
select PM_RUNTIME
|
||||||
|
|
||||||
|
config CPU_HAS_PMU
|
||||||
|
depends on CPU_SH4 || CPU_SH4A
|
||||||
|
default y
|
||||||
|
bool
|
||||||
|
|
||||||
if SUPERH32
|
if SUPERH32
|
||||||
|
|
||||||
choice
|
choice
|
||||||
|
@ -738,6 +743,14 @@ config GUSA_RB
|
||||||
LLSC, this should be more efficient than the other alternative of
|
LLSC, this should be more efficient than the other alternative of
|
||||||
disabling interrupts around the atomic sequence.
|
disabling interrupts around the atomic sequence.
|
||||||
|
|
||||||
|
config HW_PERF_EVENTS
|
||||||
|
bool "Enable hardware performance counter support for perf events"
|
||||||
|
depends on PERF_EVENTS && CPU_HAS_PMU
|
||||||
|
default y
|
||||||
|
help
|
||||||
|
Enable hardware performance counter support for perf events. If
|
||||||
|
disabled, perf events will use software events only.
|
||||||
|
|
||||||
source "drivers/sh/Kconfig"
|
source "drivers/sh/Kconfig"
|
||||||
|
|
||||||
endmenu
|
endmenu
|
||||||
|
|
|
@ -6,4 +6,8 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
|
||||||
oprofilefs.o oprofile_stats.o \
|
oprofilefs.o oprofile_stats.o \
|
||||||
timer_int.o )
|
timer_int.o )
|
||||||
|
|
||||||
|
ifeq ($(CONFIG_HW_PERF_EVENTS),y)
|
||||||
|
DRIVER_OBJS += $(addprefix ../../../drivers/oprofile/, oprofile_perf.o)
|
||||||
|
endif
|
||||||
|
|
||||||
oprofile-y := $(DRIVER_OBJS) common.o backtrace.o
|
oprofile-y := $(DRIVER_OBJS) common.o backtrace.o
|
||||||
|
|
|
@ -17,114 +17,45 @@
|
||||||
#include <linux/init.h>
|
#include <linux/init.h>
|
||||||
#include <linux/errno.h>
|
#include <linux/errno.h>
|
||||||
#include <linux/smp.h>
|
#include <linux/smp.h>
|
||||||
|
#include <linux/perf_event.h>
|
||||||
#include <asm/processor.h>
|
#include <asm/processor.h>
|
||||||
#include "op_impl.h"
|
|
||||||
|
|
||||||
static struct op_sh_model *model;
|
|
||||||
|
|
||||||
static struct op_counter_config ctr[20];
|
|
||||||
|
|
||||||
|
#ifdef CONFIG_HW_PERF_EVENTS
|
||||||
extern void sh_backtrace(struct pt_regs * const regs, unsigned int depth);
|
extern void sh_backtrace(struct pt_regs * const regs, unsigned int depth);
|
||||||
|
|
||||||
static int op_sh_setup(void)
|
char *op_name_from_perf_id(void)
|
||||||
{
|
{
|
||||||
/* Pre-compute the values to stuff in the hardware registers. */
|
const char *pmu;
|
||||||
model->reg_setup(ctr);
|
char buf[20];
|
||||||
|
int size;
|
||||||
|
|
||||||
/* Configure the registers on all cpus. */
|
pmu = perf_pmu_name();
|
||||||
on_each_cpu(model->cpu_setup, NULL, 1);
|
if (!pmu)
|
||||||
|
return NULL;
|
||||||
|
|
||||||
return 0;
|
size = snprintf(buf, sizeof(buf), "sh/%s", pmu);
|
||||||
}
|
if (size > -1 && size < sizeof(buf))
|
||||||
|
return buf;
|
||||||
|
|
||||||
static int op_sh_create_files(struct super_block *sb, struct dentry *root)
|
return NULL;
|
||||||
{
|
|
||||||
int i, ret = 0;
|
|
||||||
|
|
||||||
for (i = 0; i < model->num_counters; i++) {
|
|
||||||
struct dentry *dir;
|
|
||||||
char buf[4];
|
|
||||||
|
|
||||||
snprintf(buf, sizeof(buf), "%d", i);
|
|
||||||
dir = oprofilefs_mkdir(sb, root, buf);
|
|
||||||
|
|
||||||
ret |= oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
|
|
||||||
ret |= oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
|
|
||||||
ret |= oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
|
|
||||||
ret |= oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
|
|
||||||
|
|
||||||
if (model->create_files)
|
|
||||||
ret |= model->create_files(sb, dir);
|
|
||||||
else
|
|
||||||
ret |= oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
|
|
||||||
|
|
||||||
/* Dummy entries */
|
|
||||||
ret |= oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
|
|
||||||
}
|
|
||||||
|
|
||||||
return ret;
|
|
||||||
}
|
|
||||||
|
|
||||||
static int op_sh_start(void)
|
|
||||||
{
|
|
||||||
/* Enable performance monitoring for all counters. */
|
|
||||||
on_each_cpu(model->cpu_start, NULL, 1);
|
|
||||||
|
|
||||||
return 0;
|
|
||||||
}
|
|
||||||
|
|
||||||
static void op_sh_stop(void)
|
|
||||||
{
|
|
||||||
/* Disable performance monitoring for all counters. */
|
|
||||||
on_each_cpu(model->cpu_stop, NULL, 1);
|
|
||||||
}
|
}
|
||||||
|
|
||||||
int __init oprofile_arch_init(struct oprofile_operations *ops)
|
int __init oprofile_arch_init(struct oprofile_operations *ops)
|
||||||
{
|
{
|
||||||
struct op_sh_model *lmodel = NULL;
|
|
||||||
int ret;
|
|
||||||
|
|
||||||
/*
|
|
||||||
* Always assign the backtrace op. If the counter initialization
|
|
||||||
* fails, we fall back to the timer which will still make use of
|
|
||||||
* this.
|
|
||||||
*/
|
|
||||||
ops->backtrace = sh_backtrace;
|
ops->backtrace = sh_backtrace;
|
||||||
|
|
||||||
/*
|
return oprofile_perf_init(ops);
|
||||||
* XXX
|
|
||||||
*
|
|
||||||
* All of the SH7750/SH-4A counters have been converted to perf,
|
|
||||||
* this infrastructure hook is left for other users until they've
|
|
||||||
* had a chance to convert over, at which point all of this
|
|
||||||
* will be deleted.
|
|
||||||
*/
|
|
||||||
|
|
||||||
if (!lmodel)
|
|
||||||
return -ENODEV;
|
|
||||||
if (!(current_cpu_data.flags & CPU_HAS_PERF_COUNTER))
|
|
||||||
return -ENODEV;
|
|
||||||
|
|
||||||
ret = lmodel->init();
|
|
||||||
if (unlikely(ret != 0))
|
|
||||||
return ret;
|
|
||||||
|
|
||||||
model = lmodel;
|
|
||||||
|
|
||||||
ops->setup = op_sh_setup;
|
|
||||||
ops->create_files = op_sh_create_files;
|
|
||||||
ops->start = op_sh_start;
|
|
||||||
ops->stop = op_sh_stop;
|
|
||||||
ops->cpu_type = lmodel->cpu_type;
|
|
||||||
|
|
||||||
printk(KERN_INFO "oprofile: using %s performance monitoring.\n",
|
|
||||||
lmodel->cpu_type);
|
|
||||||
|
|
||||||
return 0;
|
|
||||||
}
|
}
|
||||||
|
|
||||||
void oprofile_arch_exit(void)
|
void __exit oprofile_arch_exit(void)
|
||||||
{
|
{
|
||||||
if (model && model->exit)
|
oprofile_perf_exit();
|
||||||
model->exit();
|
|
||||||
}
|
}
|
||||||
|
#else
|
||||||
|
int __init oprofile_arch_init(struct oprofile_operations *ops)
|
||||||
|
{
|
||||||
|
pr_info("oprofile: hardware counters not available\n");
|
||||||
|
return -ENODEV;
|
||||||
|
}
|
||||||
|
void __exit oprofile_arch_exit(void) {}
|
||||||
|
#endif /* CONFIG_HW_PERF_EVENTS */
|
||||||
|
|
|
@ -1,33 +0,0 @@
|
||||||
#ifndef __OP_IMPL_H
|
|
||||||
#define __OP_IMPL_H
|
|
||||||
|
|
||||||
/* Per-counter configuration as set via oprofilefs. */
|
|
||||||
struct op_counter_config {
|
|
||||||
unsigned long enabled;
|
|
||||||
unsigned long event;
|
|
||||||
|
|
||||||
unsigned long count;
|
|
||||||
|
|
||||||
/* Dummy values for userspace tool compliance */
|
|
||||||
unsigned long kernel;
|
|
||||||
unsigned long user;
|
|
||||||
unsigned long unit_mask;
|
|
||||||
};
|
|
||||||
|
|
||||||
/* Per-architecture configury and hooks. */
|
|
||||||
struct op_sh_model {
|
|
||||||
void (*reg_setup)(struct op_counter_config *);
|
|
||||||
int (*create_files)(struct super_block *sb, struct dentry *dir);
|
|
||||||
void (*cpu_setup)(void *dummy);
|
|
||||||
int (*init)(void);
|
|
||||||
void (*exit)(void);
|
|
||||||
void (*cpu_start)(void *args);
|
|
||||||
void (*cpu_stop)(void *args);
|
|
||||||
char *cpu_type;
|
|
||||||
unsigned char num_counters;
|
|
||||||
};
|
|
||||||
|
|
||||||
/* arch/sh/oprofile/common.c */
|
|
||||||
extern void sh_backtrace(struct pt_regs * const regs, unsigned int depth);
|
|
||||||
|
|
||||||
#endif /* __OP_IMPL_H */
|
|
Loading…
Reference in a new issue